CN103399896B - The method and system of incidence relation between identification user - Google Patents
The method and system of incidence relation between identification user Download PDFInfo
- Publication number
- CN103399896B CN103399896B CN201310314055.5A CN201310314055A CN103399896B CN 103399896 B CN103399896 B CN 103399896B CN 201310314055 A CN201310314055 A CN 201310314055A CN 103399896 B CN103399896 B CN 103399896B
- Authority
- CN
- China
- Prior art keywords
- face
- user
- photograph album
- cloud photograph
- incidence relation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The present invention provide it is a kind of identification user between incidence relation method and system, the described method comprises the following steps: obtaining the photo in several user's cloud photograph albums；Recognition of face is carried out to the photo in acquired each user's cloud photograph album respectively, obtains the corresponding face database of each user's cloud photograph album；The corresponding face database of each user's cloud photograph album is subjected to matching comparison；The incidence relation between each user is determined according to the matching comparison result.The method and system of the embodiment of the present invention take full advantage of the face under user's cloud photograph album in photo and carry out recognition of face, the incidence relation between automatic identification cloud photograph album user, to realize that the functional bands such as friend recommendation carry out great convenience.
Description
Technical field
The present invention relates to pattern-recognition and network data excavation fields, more particularly to incidence relation between a kind of identification user
Method and it is a kind of identification user between incidence relation system.
Background technique
With the development of instant messaging technology, interpersonal communication becomes more and more convenient.But it is carrying out immediately
Before communication, the object for carrying out instant messaging is needed to be necessarily present in the buddy list of user, otherwise needed through certain side
Formula finds the object of instant messaging and is added to the buddy list of user.It, can be by identifying when carrying out good friend's addition
Incidence relation between different user is to carry out the friend recommendation etc. of active.
In addition, as mobile terminal (such as mobile phone, tablet computer) becomes the application tool of the most frequently used most diversification of the mankind,
One of the application that cloud storage is most popular at mobile terminal, the also favor by numerous users of cloud photograph album.Currently, cloud photograph album is several
Become mobile terminal user's photo storage with back up it is necessary, then, the social application based on cloud photograph album also generates therewith.
It is understood that the social application based on cloud photograph album is based on photo captured by different user, therefore theoretically should
Determine the incidence relation between user, according to the characteristic of photo to realize that such as photo is given back, friend recommendation function.So
And the method for incidence relation is mostly to obtain user by the linking relationship (i.e. friend relation) between user between traditional identification user
Friend relation figure, the potential friend relation of user is then analyzed according to the structure of the friend relation figure；It can be seen that it is not
The characteristic for making full use of photo itself causes the result of incidence relation between the user identified not accurate enough.
Therefore, the incidence relation between different user how is recognized accurately, it has also become industry researcher is most interested in
One of problem.
Summary of the invention
Based on this, the present invention provide it is a kind of identification user between incidence relation method and system, can be recognized accurately not
With the incidence relation between user.
To achieve the above object, the embodiment of the present invention adopts the following technical scheme that:
A method of incidence relation between identification user, comprising the following steps:
Obtain the photo in several user's cloud photograph albums；
Recognition of face is carried out to the photo in acquired each user's cloud photograph album respectively, it is corresponding to obtain each user's cloud photograph album
Face database；
The corresponding face database of each user's cloud photograph album is subjected to matching comparison；
The incidence relation between each user is determined according to the matching comparison result.
It is a kind of identification user between incidence relation system, comprising:
Photo obtains module, for obtaining the photo in several user's cloud photograph albums；
Face recognition module is obtained for carrying out recognition of face to the photo in acquired each user's cloud photograph album respectively
The corresponding face database of each user's cloud photograph album；
Match comparison module, for the corresponding face database of each user's cloud photograph album to be carried out matching comparison；
Incidence relation determining module, for determining the incidence relation between each user according to the matching comparison result.
By one of embodiment of the present invention it can be seen from above scheme identify user between incidence relation method and be
System, by carrying out recognition of face to the photo in different cloud user photograph albums, and according to face recognition result by each user's cloud phase
The corresponding face database of volume carries out matching comparison, so that it is determined that the incidence relation between different user.The method of the embodiment of the present invention and
System excavates the profound relationship between cloud photograph album user according to recognition of face, takes full advantage of photo under user's cloud photograph album
In face carry out recognition of face, the incidence relation between automatic identification cloud photograph album user, to realize that the functional bands such as friend recommendation are come
Great convenience.
Detailed description of the invention
The flow diagram of Fig. 1 method of incidence relation between identification user a kind of in one embodiment of the invention；
Fig. 2 is the flow diagram that face recognition process is carried out in the embodiment of the present invention；
The flow diagram of Fig. 3 method of incidence relation between identification user a kind of in another embodiment of the present invention；
The structural schematic diagram of Fig. 4 system of incidence relation between identification user a kind of in one embodiment of the invention；
The structural schematic diagram of Fig. 5 system of incidence relation between identification user a kind of in another embodiment of the present invention.
Specific embodiment
It is described in detail below in conjunction with scheme of the better embodiment therein to the embodiment of the present invention.
Embodiment one
It is shown in Figure 1, a method of incidence relation between identification user, comprising the following steps:
Step S101 obtains the photo in several user's cloud photograph albums, subsequently into step S102.
In one of the embodiments, before the photo that the step S101 obtains in each cloud photograph album, can also include
Following steps: the photo that each mobile terminal uploads is received, and corresponding cloud photograph album is respectively created according to the photo received, as
Each user, creation personal cloud photograph album.
Step S102 carries out recognition of face to the photo in acquired each user's cloud photograph album respectively, obtains each user
The corresponding face database of cloud photograph album, subsequently into step S103.
In one of the embodiments, as shown in Fig. 2, the process for carrying out recognition of face can specifically include following step
It is rapid:
Step S1021 carries out Face datection to the photo in acquired each cloud photograph album, obtains facial image；
Step S1022 carries out the detection and positioning, facial feature localization and Attitude Calculation of human eye to the facial image；
Step S1023 carries out the size normalized and posture correction process of face；
Step S1024 extracts the high dimensional feature of face, and obtains the face database according to the high dimensional feature of the face,
A cloud photograph album corresponds to a face database i.e. in the embodiment of the present invention, and all faces occurred on the photo in the cloud photograph album wrap
It includes in the corresponding face database.
The high dimensional feature of the face may include Gabor characteristic and LBP(Local in one of the embodiments,
Binary Patterns, local binary patterns) feature.
It should be noted that the detection and positioning, facial feature localization, Attitude Calculation, size of above-mentioned carry out Face datection, human eye
Normalized and posture correction process etc. can use prior art, and it will not go into details herein.
The corresponding face database of each user's cloud photograph album is carried out matching comparison, subsequently into step S104 by step S103.
Step S104 determines the incidence relation between each user according to the matching comparison result.
Embodiment two
The method that one of the present embodiment identifies incidence relation between user, as shown in Figure 3, comprising the following steps:
Step S201 obtains the photo in several user's cloud photograph albums, subsequently into step S202.
Step S202 carries out recognition of face to the photo in acquired each user's cloud photograph album respectively, obtains each user
The corresponding face database of cloud photograph album, subsequently into step S203.
Step S203, in some cases, the face number in the face database of a cloud photograph album may be relatively more, such as
There are 100 faces, and there are some faces to repeat here, such as the same person appears in the feelings on multiple pictures
Condition.At this time in the present embodiment, hierarchical clustering can be carried out to the face in the face database after obtaining the face database,
Face similar in the face database is determined as a face, subsequently into step S204.
Further, in one of the embodiments, it is described carry out hierarchical clustering process can specifically include it is as follows:
Absolute distance and relative distance between face are calculated according to the index, when the absolute distance and relative distance
Respectively less than preset threshold when face is merged；
The result merged according to face gathers similar face for one kind, and refreshes the two of class neighbour and class as unit of class
Minor sort score；
Merging for class is carried out with relative distance according to the absolute distance between class, is until there is no the classes that can merge
Only, the face group is obtained.
It should be noted that the absolute distance between above-mentioned face refer to certain face and its neighbour's face high dimensional feature it
Between COS distance；Relative distance between the face, which refers to, to be calculated according to the shared nearest neighbor of two faces with neighbour's sequence
The secondary Sorting distance of two faces out；In addition, the absolute distance between class refers to the exhausted of face nearest between two classes
It adjusts the distance.
Through the above steps, it can remove those duplicate faces in a face database, reduce face in face database
Number carries out the time spent in operation is compared in matching to save in subsequent step.
Step S204, what is different from the first embodiment is that by the corresponding face database of each user's cloud photograph album in the present embodiment
Further include following steps before carrying out matching comparison:
Face in each face database is compared with the face in public figure's face database, excludes user's cloud photograph album pair
The public figure's face for including in the face database answered, subsequently into step S205.Subsequent match ratio can be further speeded up in this way
Compared with the execution speed of operation.
The corresponding face database of each user's cloud photograph album is carried out matching comparison by step S205.In the present embodiment, it is described will be each
The process that the corresponding face database of a user's cloud photograph album carries out matching comparison can specifically include following steps: obtain each face database
In each face identification feature, judge whether there is identical face (the i.e. cloud photograph album of user i and user j in any two face database
In whether have identical personage), subsequently into step S206.
Step S206 determines the incidence relation between each user.Incidence relation in the present embodiment, between each user of determination
Process can specifically include following steps: if there is identical face in any two face database, illustrate it is corresponding the two use
There is certain incidence relation between family, then the corresponding cloud photograph album user of the face database can mutually be recommended to the cloud of other side
Photograph album user terminal.
Embodiment three
The method of incidence relation is corresponding between a kind of above-mentioned identification user, and the embodiment of the present invention also provides a kind of identification and uses
The system of incidence relation between family, as shown in Figure 4, comprising:
Photo obtains module 101, for obtaining the photo in several user's cloud photograph albums；
Face recognition module 102 is obtained for carrying out recognition of face to the photo in acquired each user's cloud photograph album respectively
To the corresponding face database of each user's cloud photograph album；
Match comparison module 103, for the corresponding face database of each user's cloud photograph album to be carried out matching comparison；
Incidence relation determining module 104, for determining the incidence relation between each user according to the matching comparison result.
May include: in the face recognition module in one of the embodiments,
Face detection module obtains facial image for carrying out Face datection to the photo in acquired each cloud photograph album；
Positioning and computing module, for carrying out the detection and positioning, facial feature localization and appearance of human eye to the facial image
State calculates；
Normalization and correction process module, for carrying out the size normalized and posture correction process of face；
Characteristic extracting module is distinguished for extracting the high dimensional feature of face, and according to the high dimensional feature of the face
Belong to the face database of each cloud photograph album.
It should be noted that the detection and positioning, facial feature localization, Attitude Calculation, size of above-mentioned carry out Face datection, human eye
Normalized and posture correction process etc. can use prior art, and it will not go into details herein.
The high dimensional feature of the face may include Gabor characteristic and LBP feature etc. in one of the embodiments,.
In one of the embodiments, as shown in figure 5, may include cluster module in the face recognition module, it is used for
After obtaining the face database, hierarchical clustering is carried out to the face in the face database, by people similar in the face database
Face is determined as a face.The detailed process of above-mentioned hierarchical clustering is associated with pass between can be found in one of embodiment two identification user
Associated description in the method for system can remove those duplicate faces in a face database by the cluster module, reduce people
The number of face in face library, so that saving match comparison module carries out the time spent in operation is compared in matching.
In one of the embodiments, as shown in figure 5, may include friend recommendation mould in the incidence relation determining module
Block, for according to the match comparison module export as a result, whether prompt by the corresponding cloud photograph album user of face database carries out phase
Mutually recommend to the cloud photograph album user terminal of other side.
In one of the embodiments, as shown in figure 5, the system of incidence relation can also include public affairs between the identification user
Everybody's object face database, correspondingly, may include that public figure's face excludes module, the public figure in the match comparison module
Face exclude module be used for it is described the corresponding face database of each user's cloud photograph album is subjected to matching comparison before, by each face
Face in library is compared with the face in public figure's face database, excludes to wrap in the corresponding face database of user's cloud photograph album
The public figure's face contained.
Other technical characteristics of the system of incidence relation and a kind of knowledge in the embodiment of the present invention between a kind of above-mentioned identification user
The method of incidence relation is identical between other user, and it will not go into details herein.
By above scheme as can be seen that one of embodiment of the present invention identification user between incidence relation method and be
System, by carrying out recognition of face to the photo in different cloud user photograph albums, and according to face recognition result by each user's cloud phase
The corresponding face database of volume carries out matching comparison, so that it is determined that the incidence relation between different user.The method of the embodiment of the present invention and
System excavates the profound relationship between cloud photograph album user according to recognition of face, takes full advantage of photo under user's cloud photograph album
In face carry out recognition of face, the incidence relation between automatic identification cloud photograph album user, to realize that the functional bands such as friend recommendation are come
Great convenience.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
The embodiments described above only express several embodiments of the present invention, and the description thereof is more specific and detailed, but simultaneously
Limitations on the scope of the patent of the present invention therefore cannot be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to guarantor of the invention
Protect range.Therefore, the scope of protection of the patent of the invention shall be subject to the appended claims.
Claims (10)
1. a kind of method of incidence relation between identification user, which comprises the following steps:
Obtain the photo in several user's cloud photograph albums；
Recognition of face is carried out to the photo in acquired each user's cloud photograph album respectively, obtains the corresponding people of each user's cloud photograph album
Face library；All faces occurred on photo in the cloud photograph album are included in the corresponding face database；
The corresponding face database of each user's cloud photograph album is subjected to matching comparison；
The incidence relation between each user is determined according to the matching comparison result；
Wherein, the incidence relation between each user of the determination is the following steps are included: if there is identical face in any two face database,
The corresponding cloud photograph album user of the face database is then mutually recommended to the cloud photograph album user terminal of other side；
The process for carrying out recognition of face includes: to carry out hierarchical clustering to the face in the face database, by the face database
In similar face be determined as a face；
The face in the face database carry out hierarchical clustering include: calculate absolute distance between face and it is opposite away from
From face is merged when the absolute distance is respectively less than preset threshold with relative distance；The result merged according to face
Similar face is gathered for one kind, and refreshes the two minor sort scores of class neighbour and class as unit of class；According to exhausted between class
It adjusts the distance and carries out merging for class with relative distance, until there is no the class that can merge, obtain face group；
Absolute distance between the face refers to the COS distance between certain face and the high dimensional feature of its neighbour's face；It is described
Relative distance between face refers to according to two calculated faces of the shared nearest neighbor of two faces and neighbour's sequence
Secondary Sorting distance.
2. the method for incidence relation between identification user according to claim 1, which is characterized in that the carry out recognition of face
Process include:
Face datection is carried out to the photo in acquired each user's cloud photograph album, obtains facial image；
The detection and positioning, facial feature localization and Attitude Calculation of human eye are carried out to the facial image；
Carry out the size normalized and posture correction process of face；
The high dimensional feature of face is extracted, and the face database is obtained according to the high dimensional feature of the face.
3. the method for incidence relation between identification user according to claim 1 or 2, which is characterized in that described by each use
The corresponding face database of family cloud photograph album carry out matching comparison process the following steps are included:
The identification feature for obtaining each face in each face database judges whether there is identical face in any two face database.
4. the method for incidence relation between identification user according to claim 1, which is characterized in that absolute between the class
Distance refers to the absolute distance of face nearest between two classes.
5. the method for incidence relation between identification user according to claim 4, which is characterized in that described by each user
Before the corresponding face database of cloud photograph album carries out matching comparison, further comprise the steps of:
Face in each face database is compared with the face in public figure's face database, it is corresponding to exclude user's cloud photograph album
The public figure's face for including in face database.
6. the system of incidence relation between a kind of identification user characterized by comprising
Photo obtains module, for obtaining the photo in several user's cloud photograph albums；
Face recognition module obtains each for carrying out recognition of face to the photo in acquired each user's cloud photograph album respectively
The corresponding face database of user's cloud photograph album；All faces occurred on photo in the cloud photograph album are included in the corresponding face
In library；
Match comparison module, for the corresponding face database of each user's cloud photograph album to be carried out matching comparison；
Incidence relation determining module, for determining the incidence relation between each user according to the matching comparison result；
Wherein, the incidence relation determining module is also used to: if there is identical face in any two face database, by the face database
Corresponding cloud photograph album user is mutually recommended to the cloud photograph album user terminal of other side；
It include cluster module in the face recognition module, for after obtaining the face database, in the face database
Face carries out hierarchical clustering, and face similar in the face database is determined as a face；
The face in the face database carry out hierarchical clustering include: calculate absolute distance between face and it is opposite away from
From face is merged when the absolute distance is respectively less than preset threshold with relative distance；The result merged according to face
Similar face is gathered for one kind, and refreshes the two minor sort scores of class neighbour and class as unit of class；According to exhausted between class
It adjusts the distance and carries out merging for class with relative distance, until there is no the class that can merge, obtain face group；
Absolute distance between the face refers to the COS distance between certain face and the high dimensional feature of its neighbour's face；It is described
Relative distance between face refers to according to two calculated faces of the shared nearest neighbor of two faces and neighbour's sequence
Secondary Sorting distance.
7. the system of incidence relation between identification user according to claim 6, which is characterized in that the incidence relation determines
Include friend recommendation module in module, for according to the match comparison module export as a result, whether prompting by face database pair
The cloud photograph album user answered is mutually recommended to the cloud photograph album user terminal of other side.
8. the system of incidence relation between identification user according to claim 7, which is characterized in that further include public figure people
Face library, and
It include that public figure's face excludes module in the match comparison module, for described that each user's cloud photograph album is corresponding
Face database carry out matching comparison before, by each face database face and public figure's face database in face carry out
Compare, excludes the public figure's face for including in the corresponding face database of user's cloud photograph album.
9. a kind of storage medium, is stored thereon with computer program, which is characterized in that described program is executed by processor Shi Keshi
Now as described in any one of claims 1 to 5 identification user between incidence relation method.
10. a kind of terminal device, including storage medium, processor and storage can be run on a storage medium and on a processor
Computer program, the processor are realized when executing described program between the identification user as described in any one of claims 1 to 5
The method of incidence relation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310314055.5A CN103399896B (en) | 2013-07-19 | 2013-07-19 | The method and system of incidence relation between identification user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310314055.5A CN103399896B (en) | 2013-07-19 | 2013-07-19 | The method and system of incidence relation between identification user |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103399896A CN103399896A (en) | 2013-11-20 |
| CN103399896B true CN103399896B (en) | 2019-08-23 |
Family
ID=49563526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310314055.5A Active CN103399896B (en) | 2013-07-19 | 2013-07-19 | The method and system of incidence relation between identification user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103399896B (en) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103970830B (en) * | 2014-03-31 | 2017-06-16 | 小米科技有限责任公司 | Information recommendation method and device |
| CN104333506A (en) * | 2014-10-24 | 2015-02-04 | 北京兴远永网络科技有限公司 | Communication terminal contact method and device |
| CN105630791B (en) * | 2014-10-27 | 2020-11-10 | 腾讯科技（深圳）有限公司 | Network album browsing method and device |
| CN104852967B (en) * | 2015-04-21 | 2018-03-27 | 小米科技有限责任公司 | Image sharing method and device |
| CN104991910B (en) * | 2015-06-19 | 2018-12-11 | 小米科技有限责任公司 | Photograph album creation method and device |
| CN106330658A (en) * | 2015-06-23 | 2017-01-11 | 腾讯科技（深圳）有限公司 | Internet-based information association method, terminal, server and system |
| CN106326815B (en) * | 2015-06-30 | 2019-09-13 | 芋头科技（杭州）有限公司 | A kind of facial image recognition method |
| CN105069083B (en) | 2015-07-31 | 2019-03-08 | 小米科技有限责任公司 | The determination method and device of association user |
| CN105243098B (en) * | 2015-09-16 | 2018-10-26 | 小米科技有限责任公司 | The clustering method and device of facial image |
| CN105631404B (en) * | 2015-12-17 | 2018-11-30 | 小米科技有限责任公司 | The method and device that photo is clustered |
| CN107526735B (en) * | 2016-06-20 | 2020-12-11 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying incidence relation |
| CN107292252B (en) * | 2017-06-09 | 2020-09-15 | 南京华捷艾米软件科技有限公司 | Identity recognition method for autonomous learning |
| CN107451287A (en) * | 2017-08-14 | 2017-12-08 | 佛山科学技术学院 | A kind of recommendation method based on bi-directional matching |
| CN110084709A (en) * | 2018-01-23 | 2019-08-02 | 百度在线网络技术（北京）有限公司 | Good friend's processing method, server and computer-readable medium based on facial characteristics |
| CN108446681B (en) * | 2018-05-10 | 2020-12-15 | 深圳云天励飞技术有限公司 | Pedestrian analysis method, device, terminal and storage medium |
| CN113961900A (en) * | 2018-07-16 | 2022-01-21 | 创新先进技术有限公司 | Identity authentication method and device |
| CN111428549A (en) * | 2019-10-31 | 2020-07-17 | 深圳市睿洋图志科技有限公司 | Social moving image big data-based character information analysis method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101446961A (en) * | 2008-12-24 | 2009-06-03 | 腾讯科技（深圳）有限公司 | Method and system for carrying out association on users and friends thereof in network community |
| CN102355534A (en) * | 2011-11-01 | 2012-02-15 | 宇龙计算机通信科技(深圳)有限公司 | Mobile terminal and contact information recommendation method |
| CN102831176A (en) * | 2012-07-30 | 2012-12-19 | 东莞宇龙通信科技有限公司 | Method and server for recommending friends |
| CN102843453A (en) * | 2012-08-14 | 2012-12-26 | 广东欧珀移动通信有限公司 | Address list relationship adding method and mobile terminal |
-
2013
- 2013-07-19 CN CN201310314055.5A patent/CN103399896B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101446961A (en) * | 2008-12-24 | 2009-06-03 | 腾讯科技（深圳）有限公司 | Method and system for carrying out association on users and friends thereof in network community |
| CN102355534A (en) * | 2011-11-01 | 2012-02-15 | 宇龙计算机通信科技(深圳)有限公司 | Mobile terminal and contact information recommendation method |
| CN102831176A (en) * | 2012-07-30 | 2012-12-19 | 东莞宇龙通信科技有限公司 | Method and server for recommending friends |
| CN102843453A (en) * | 2012-08-14 | 2012-12-26 | 广东欧珀移动通信有限公司 | Address list relationship adding method and mobile terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103399896A (en) | 2013-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103399896B (en) | The method and system of incidence relation between identification user | |
| CN107633207B (en) | AU characteristic recognition methods, device and storage medium | |
| EP3248143B1 (en) | Reducing computational resources utilized for training an image-based classifier | |
| CN103207898B (en) | A kind of similar face method for quickly retrieving based on local sensitivity Hash | |
| US11361019B2 (en) | Image query method and apparatus | |
| CN109190514B (en) | Face attribute recognition method and system based on bidirectional long-short term memory network | |
| Abdullah et al. | Towards population scale activity recognition: A framework for handling data diversity | |
| CN106778450A (en) | A kind of face recognition method and device | |
| CN104915351A (en) | Picture sorting method and terminal | |
| CN103778409A (en) | Human face identification method based on human face characteristic data mining and device | |
| CN108596944A (en) | A kind of method, apparatus and terminal device of extraction moving target | |
| CN102890776A (en) | Method for searching emoticons through facial expression | |
| CN110741387B (en) | Face recognition method and device, storage medium and electronic equipment | |
| CN111814923B (en) | Image clustering method, system, device and medium | |
| CN102890777B (en) | The computer system of recognizable facial expression | |
| CN109426785A (en) | A kind of human body target personal identification method and device | |
| EP3779775A1 (en) | Media processing method and related apparatus | |
| CN102637255A (en) | Method and device for processing faces contained in images | |
| Petkos et al. | Graph-based multimodal clustering for social event detection in large collections of images | |
| CN105631404B (en) | The method and device that photo is clustered | |
| CN112966643A (en) | Face and iris fusion recognition method and device based on self-adaptive weighting | |
| CN103870812A (en) | Method and system for acquiring palmprint image | |
| CN109088788A (en) | Data processing method, device, equipment and computer readable storage medium | |
| EP3200092A1 (en) | Method and terminal for implementing image sequencing | |
| Karappa et al. | Detection of sign-language content in video through polar motion profiles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 511449 Guangzhou City, Guangdong Province, Panyu District, South Village, Huambo Business District Wanda Plaza, block B1, floor 28 Applicant after: Guangzhou Huaduo Network Technology Co., Ltd. Address before: 510655, Guangzhou, Tianhe District, Whampoa Avenue, No. 309, creative park, building 3-08 Applicant before: Guangzhou Huaduo Network Technology Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |